SegGPTOptions
Options & Configuration · AiDotNet.ComputerVision.Segmentation.Interactive
Configuration options for SegGPT in-context segmentation.
Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → SegmentationModelOptions → SegGPTOptions
For Beginners
These options configure the SegGPT model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
SegGPTOptions() |
Initializes a new instance with default values. |
SegGPTOptions(SegGPTOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
SegGPTModelSize ModelSize { get; set; } |
Gets or sets which published size variant of the model to build. |
int DecoderDimension { get; set; } |
Gets or sets the mask decoder width. |
int[] ChannelDimensions { get; set; } |
Gets or sets the four hierarchical encoder widths. |
int[] StageDepths { get; set; } |
Gets or sets the number of blocks in each encoder stage. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Throws when a value on this instance cannot produce a working model. |